VideoGameBunny: Towards vision assistants for video games
This work addresses the problem of inaccurate scene understanding and hallucinations in video games for AI researchers and developers, representing an incremental improvement with domain-specific data.
The paper tackles the limitations of large multimodal models in understanding video game content by developing VideoGameBunny, a tailored model that outperforms a much larger state-of-the-art model (LLaVa-1.6-34b) despite having over 4x fewer parameters.
Large multimodal models (LMMs) hold substantial promise across various domains, from personal assistance in daily tasks to sophisticated applications like medical diagnostics. However, their capabilities have limitations in the video game domain, such as challenges with scene understanding, hallucinations, and inaccurate descriptions of video game content, especially in open-source models. This paper describes the development of VideoGameBunny, a LLaVA-style model based on Bunny, specifically tailored for understanding images from video games. We release intermediate checkpoints, training logs, and an extensive dataset comprising 185,259 video game images from 413 titles, along with 389,565 image-instruction pairs that include image captions, question-answer pairs, and a JSON representation of 16 elements of 136,974 images. Our experiments show that our high quality game-related data has the potential to make a relatively small model outperform the much larger state-of-the-art model LLaVa-1.6-34b (which has more than 4x the number of parameters). Our study paves the way for future research in video game understanding on tasks such as playing, commentary, and debugging. Code and data are available at https://videogamebunny.github.io/